Integrating Spatiotemporal Features in LSTM for Spatially Informed COVID-19 Hospitalization Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916844927975424 |
|---|---|
| author | Wang, Zhongying Ngo, Thoai D. Zoraghein, Hamidreza Lucas, Benjamin Karimzadeh, Morteza |
| author_facet | Wang, Zhongying Ngo, Thoai D. Zoraghein, Hamidreza Lucas, Benjamin Karimzadeh, Morteza |
| contents | The COVID-19 pandemic's severe impact highlighted the need for accurate and timely hospitalization forecasting to support effective healthcare planning. However, most forecasting models struggled, particularly during variant surges, when they were most needed. This study introduces a novel parallel-stream Long Short-Term Memory (LSTM) framework to forecast daily state-level incident hospitalizations in the United States. Our framework incorporates a spatiotemporal feature, Social Proximity to Hospitalizations (SPH), derived from Meta's Social Connectedness Index, to improve forecasts. SPH serves as a proxy for interstate population interaction, capturing transmission dynamics across space and time. Our architecture captures both short- and long-term temporal dependencies, and a multi-horizon ensembling strategy balances forecasting consistency and error. An evaluation against the COVID-19 Forecast Hub ensemble models during the Delta and Omicron surges reveals the superiority of our model. On average, our model surpasses the ensemble by 27, 42, 54, and 69 hospitalizations per state at the 7-, 14-, 21-, and 28-day horizons, respectively, during the Omicron surge. Data-ablation experiments confirm SPH's predictive power, highlighting its effectiveness in enhancing forecasting models. This research not only advances hospitalization forecasting but also underscores the significance of spatiotemporal features, such as SPH, in modeling the complex dynamics of infectious disease spread. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating Spatiotemporal Features in LSTM for Spatially Informed COVID-19 Hospitalization Forecasting Wang, Zhongying Ngo, Thoai D. Zoraghein, Hamidreza Lucas, Benjamin Karimzadeh, Morteza Machine Learning Artificial Intelligence The COVID-19 pandemic's severe impact highlighted the need for accurate and timely hospitalization forecasting to support effective healthcare planning. However, most forecasting models struggled, particularly during variant surges, when they were most needed. This study introduces a novel parallel-stream Long Short-Term Memory (LSTM) framework to forecast daily state-level incident hospitalizations in the United States. Our framework incorporates a spatiotemporal feature, Social Proximity to Hospitalizations (SPH), derived from Meta's Social Connectedness Index, to improve forecasts. SPH serves as a proxy for interstate population interaction, capturing transmission dynamics across space and time. Our architecture captures both short- and long-term temporal dependencies, and a multi-horizon ensembling strategy balances forecasting consistency and error. An evaluation against the COVID-19 Forecast Hub ensemble models during the Delta and Omicron surges reveals the superiority of our model. On average, our model surpasses the ensemble by 27, 42, 54, and 69 hospitalizations per state at the 7-, 14-, 21-, and 28-day horizons, respectively, during the Omicron surge. Data-ablation experiments confirm SPH's predictive power, highlighting its effectiveness in enhancing forecasting models. This research not only advances hospitalization forecasting but also underscores the significance of spatiotemporal features, such as SPH, in modeling the complex dynamics of infectious disease spread. |
| title | Integrating Spatiotemporal Features in LSTM for Spatially Informed COVID-19 Hospitalization Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.05752 |